Title: Post hoc Interpretability: Review on New Frontiers of Interpretable AI
Abstract: In order to make critical decisions, organizations are increasingly using sophisticated black box machine learning algorithms. Post hoc interpretability techniques are a well-liked solution to the issue of transparency in black box machine learning algorithms. These techniques try to explain the internal workings of the underlying machine learning models so that stakeholders can comprehend them. This paper suggests that post hoc interpretability approaches’ insights can be used to control black box machine learning. The veracity of these statements is investigated in this article. This paper discusses the post hoc interpretability methods on individual prediction. The paper provides detailed comparison of post hoc interpretability methods, software packages, and interpretability toolkits available in market.
Publication Year: 2023
Publication Date: 2023-01-01
Language: en
Type: book-chapter
Indexed In: ['crossref']
Access and Citation
Cited By Count: 1
AI Researcher Chatbot
Get quick answers to your questions about the article from our AI researcher chatbot